{"id":"https://openalex.org/W7225730151","doi":"https://doi.org/10.1007/s10791-026-10623-x","title":"An efficient spatial-temporal attention network for low-latency isolated Indian Sign Language Recognition","display_name":"An efficient spatial-temporal attention network for low-latency isolated Indian Sign Language Recognition","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225730151","doi":"https://doi.org/10.1007/s10791-026-10623-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-026-10623-x","doi":"https://doi.org/10.1007/s10791-026-10623-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-026-10623-x","pdf_url":null,"source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ccf-c","doaj","dongbi-d","jufo-3","norway-2","russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s10791-026-10623-x","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031754190","display_name":"Surbhi Maheshwari","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surbhi Maheshwari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161378259","display_name":"Amit Kumar Sinhal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Kumar Sinhal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120460308","display_name":"Arpana Sinhal","orcid":"https://orcid.org/0009-0008-2058-7685","observed_orcids":["https://orcid.org/0009-0008-2058-7685"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arpana Sinhal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1520,"currency":"USD","value_usd":1520},"apc_paid":{"value":1520,"currency":"USD","value_usd":1520},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279000282287598},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.435699999332428},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-026-10623-x","doi":"https://doi.org/10.1007/s10791-026-10623-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-026-10623-x","pdf_url":null,"source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ccf-c","doaj","dongbi-d","jufo-3","norway-2","russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10791-026-10623-x","doi":"https://doi.org/10.1007/s10791-026-10623-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-026-10623-x","pdf_url":null,"source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ccf-c","doaj","dongbi-d","jufo-3","norway-2","russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2167277498","https://openalex.org/W2550143307","https://openalex.org/W2803685074","https://openalex.org/W3015075688","https://openalex.org/W3092651828","https://openalex.org/W3157193418","https://openalex.org/W3192144883","https://openalex.org/W3198787543","https://openalex.org/W3202747033","https://openalex.org/W3206600927","https://openalex.org/W4205517074","https://openalex.org/W4291700596","https://openalex.org/W4315473456","https://openalex.org/W4366779346","https://openalex.org/W4385571151","https://openalex.org/W4386075496","https://openalex.org/W4390054296","https://openalex.org/W4391216755","https://openalex.org/W4392397356","https://openalex.org/W4392607709","https://openalex.org/W4393187948","https://openalex.org/W4399074661","https://openalex.org/W4399341414","https://openalex.org/W4400691427","https://openalex.org/W4402170719","https://openalex.org/W4402856323","https://openalex.org/W4406300803","https://openalex.org/W4407895231","https://openalex.org/W4409264125","https://openalex.org/W4409963323","https://openalex.org/W7133203375"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"About":[1],"63":[2],"million":[3],"people":[4],"in":[5,120,144,184],"India":[6],"live":[7],"with":[8,57,82,167],"significant":[9,259],"hearing":[10],"impairment,":[11],"yet":[12],"Indian":[13],"Sign":[14],"Language":[15],"(ISL)":[16],"is":[17,28,66,127,248],"still":[18],"poorly":[19],"served":[20],"by":[21],"assistive":[22],"digital":[23],"tools":[24],"even":[25],"though":[26],"it":[27,284],"central":[29],"to":[30,272,279,285,289],"communication":[31],"within":[32],"the":[33,72,75,87,121,129,134,140,208,215,219,242,245,280,336],"Deaf":[34],"and":[35,61,80,105,107,147,156,164,255,316,335],"Hard-of-Hearing":[36],"(DHH)":[37],"community.":[38],"We":[39,100],"present":[40],"STANet,":[41],"a":[42,52,92,157,168,185,196,266],"compact":[43],"hybrid":[44],"model":[45,88,337],"for":[46,212,234],"isolated":[47],"ISL":[48],"recognition":[49,299],"that":[50,150,331],"pairs":[51],"Time-Distributed":[53],"Conv2D":[54],"frame":[55],"encoder":[56,76],"causal":[58],"temporal":[59,78,200],"convolution":[60,79],"multi-head":[62],"self-attention.":[63],"The":[64,124],"contribution":[65],"not":[67,178,229,256,339],"an":[68,192,251,306,322],"individual":[69],"module":[70],"but":[71,182,275],"composition":[73],"itself:":[74],"feeds":[77],"attention":[81],"no":[83],"recurrent":[84],"layers,":[85],"so":[86,137,241],"captures":[89],"motion":[90],"across":[91,180,300],"clip":[93,135],"while":[94,207],"keeping":[95],"per-clip":[96,226],"inference":[97,304],"cost":[98],"low.":[99],"evaluate":[101],"STANet":[102,152],"on":[103,162,173,195,204,224,314,319,321,342],"INCLUDE-50":[104,315],"ISL-50":[106,320],"compare":[108],"it,":[109],"under":[110],"one":[111],"shared":[112,197],"pipeline,":[113],"against":[114],"3D":[115],"CNN":[116],"baselines":[117],"built":[118],"earlier":[119],"same":[122,141,281],"study.":[123],"main":[125],"evaluation":[126],"signer-dependent:":[128],"splits":[130],"are":[131],"stratified":[132],"at":[133,237],"level,":[136],"clips":[138],"from":[139,330],"signers":[142],"appear":[143],"both":[145],"training":[146],"test.":[148],"In":[149,191],"setting":[151],"reaches":[153],"88.36%":[154],"accuracy":[155,166,216,270],"macro":[158,169],"F1-score":[159,170],"of":[160,171,214,244],"0.8841":[161],"INCLUDE-50,":[163],"94.38%":[165],"0.9399":[172],"ISL-50.":[174],"Residual":[175],"errors":[176],"do":[177,228],"spread":[179],"classes":[181],"concentrate":[183],"few":[186],"visually":[187],"similar":[188],"sign":[189],"pairs.":[190],"encoder-controlled":[193],"ablation":[194],"backbone,":[198],"each":[199],"stage":[201],"adds":[202],"little":[203],"its":[205],"own,":[206],"two":[209,246],"together":[210],"account":[211],"most":[213],"gain":[217],"over":[218],"backbone.":[220],"Paired":[221],"McNemar":[222],"tests":[223],"those":[225],"predictions":[227],"reach":[230],"significance":[231],"once":[232],"corrected":[233],"multiple":[235],"comparisons":[236],"this":[238],"test-set":[239],"size,":[240],"complementarity":[243],"stages":[247],"reported":[249],"as":[250,257,296],"observed":[252],"effect":[253],"size":[254],"statistically":[258],"evidence.":[260],"A":[261],"separate":[262],"leave-one-signer-out":[263],"test":[264],"tells":[265],"harder":[267],"story:":[268],"RGB":[269],"falls":[271],"roughly":[273],"19%,":[274],"feeding":[276],"pose":[277,290],"landmarks":[278],"architecture":[282],"recovers":[283],"58.4%,":[286],"which":[287],"points":[288],"geometry":[291],"rather":[292],"than":[293],"raw":[294],"appearance":[295],"what":[297],"carries":[298],"signers.":[301],"Offline":[302],"clip-level":[303],"through":[305],"OpenCV":[307],"pipeline":[308],"takes":[309],"3.488":[310],"ms":[311,318],"per":[312],"sample":[313],"3.481":[317],"NVIDIA":[323],"GeForce":[324],"GTX":[325],"1650;":[326],"these":[327],"timings":[328],"come":[329],"single":[332],"desktop":[333],"GPU,":[334],"has":[338],"been":[340],"profiled":[341],"mobile":[343],"or":[344],"embedded":[345],"hardware.":[346]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}